In observational studies the overall aim when fitting a model for the propensity score is to reduce bias for an estimator of the causal effect. For this purpose guidelines for covariate selection for propensity score models have been proposed in the causal inference literature. To make the...

We exploit information on compulsory schooling reforms in 11 European countries, implemented mostly in the 1960s and 70s, to identify the impact of education on religious adherence and religious practices. Using micro data from the European Social Survey, conducted in various years between 2002...